Kenneth Stanley

@kenneth0stanley

Founding member, Uber AI Labs; UCF Prof. AI ML Neuroevolution: NEAT, HyperNEAT, novelty search. Book: Why Greatness Cannot Be Planned:

Vrijeme pridruživanja: ožujak 2016.

Tweetovi

Blokirali ste korisnika/cu @kenneth0stanley

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @kenneth0stanley

  1. proslijedio/la je Tweet
    26. sij

    This reminds me of one of my favorite 📚 of the decade, Why Greatness Cannot Be Planned by . The decision tree of life is foggy and the “right” path can’t be known. Don’t plan a route, set a *direction* and re-calibrate frequently.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    7. sij

    Introducing Deep Innovation Protection - we scale neuroevolution to more complex tasks such as "VizDoom: Take Cover" by temporally reducing the selection pressure on specific components in an evolving world model. w/

    Prikaži ovu nit
    Poništi
  3. 4. sij

    Life is not easy when you're posing next to a GAN-generated face.

    Prikaži ovu nit
    Poništi
  4. 4. sij

    Despite at least one cause being apparent (less data on faces on the periphery), it's still interesting to see the train-wreck when a photo-realistic face-trained GAN makes the unfortunate choice to place a "friend" beside the main subject... (more in reply)

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    4. sij
    Poništi
  6. proslijedio/la je Tweet
    19. pro 2019.

    Wow. 24 hours from our blog post to someone posting a web tutorial/summary of our Generative Teaching Networks! Impressively fast! work led by with and

    Poništi
  7. 18. pro 2019.

    Introducing Generative Teaching Networks - they generate synthetic data optimized to train learners as fast as possible - a new way to generate data for architecture search & more! Led by w/ , , &

    Poništi
  8. proslijedio/la je Tweet
    13. pro 2019.

    There's definitely a common philosophical thread running through 's latest essay and and Joel Lehman's "Why Greatness Cannot Be Planned"

    Poništi
  9. proslijedio/la je Tweet
    12. pro 2019.

    If you are willing to learn more about Quality-Diversity algorithms, we have created a website that gathers papers, tutorials, and implementations of QD algorithms. The progressive increase of papers published on this topic every year is impressive!

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    7. pro 2019.

    Great discussion on lifelong learning in Neural Networks, highlights work by and . Lifelong learning was a notion I wanted to study early on.

    Poništi
  11. proslijedio/la je Tweet
    6. pro 2019.

    CMA-ME (that's the acronym) builds on the ideas of quality diversity algorithms as pioneered by , in particular the MAP-Elites algorithm by , and combines this with principles of modern optimization.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    6. stu 2019.
    Odgovor korisniku/ci
    Poništi
  13. proslijedio/la je Tweet

    To create better AI, researchers are attempting to emulate the only system we’ve seen develop anything remotely like human intelligence: biological evolution.

    Poništi
  14. 6. stu 2019.

    Nice coverage by of some of the big ideas behind our work and some of the history of neuroevolution for at ...thanks for the thoughtful article!

    Poništi
  15. proslijedio/la je Tweet
    29. kol 2019.

    Lenia is now used in machine learning research! by , M Etcheverry & . They used curiosity-driven IMGEP algorithm with CPPN-NEAT and VAE to auto discover artificial life-forms, with interesting results (increased diversity).

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet

    Open-ended algorithms can offer an entirely different level of automated creation. talks more about this new grand challenge for at the conference in San Jose.

    Poništi
  17. proslijedio/la je Tweet
    23. ruj 2019.

    Infinite-resolution image generation in the browser using CPPNs, GANs and some TensorFlow.js wizardy 🧙 Check it out LIVE at 🚀🚀🚀🚀🚀🚀 ((following the naming convention of GAN websites, of course 😄)))

    Poništi
  18. proslijedio/la je Tweet
    18. kol 2019.

    Evolving Networks: A nice review article about NEAT and extensions, with a minimal python implementation. Interesting to read about Neuroevolution from people like who mainly work on Deep Learning and NLP.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    15. kol 2019.

    Sr Research Scientist is one of the many expert keynote speakers at the conference. Final weeks to register! Save your spot today.

    Poništi
  20. proslijedio/la je Tweet

    We are very proud that AI Labs' Rui Wang, Joel Lehman, Jeff Clune, and Ken Stanley won a Best Paper Award for POET, the ML algorithm released earlier this year! More about POET: Read the paper:

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·